# -*- coding: cp1252 -*-
from pyspark import SparkConf, SparkContext
import collections

sConf = SparkConf().setMaster("local").setAppName("RatingsRDDApp")
sContext = SparkContext(conf = sConf)

alllinesRDD = sContext.textFile("file:///D:/dumps/BigData/ml-100k/u.data")
allratingsRDD =alllinesRDD.map(lambda line: line.split()[2])
resultRDD= allratingsRDD.countByValue()

sortedResultsRDD = collections.OrderedDict(sorted(resultRDD.items()))
for rddKey, rddValue in sortedResultsRDD.items():
    print("%s %i" % (rddKey, rddValue))